In order for intelligent systems to be a viable and utilized tool, a user must be able to understand how the system comes to a decision. Without understanding how the system arrived at an answer, a user will be less likely to trust its decision. One way to increase a user's understanding of how the system functions is by employing explanations to account for the output produced. There have been attempts to explain intelligent systems over the past three decades. However, each attempt has had shortcomings that separated the logic used to produce the output and that used to produce the explanation. By using the representational paradigm of Contextual Graphs, it is proposed that explanations can be produced to overcome these shortcomings. Two different temporal forms of explanations are proposed, a pre-explanation and a post-explanation. The pre-explanation is intended to help the user understand the decision making process. The post-explanation is intended to help the user understand how the system arrived at a final decision. Both explanations are intended to help the user gain a greater understanding of the logic used to compute the system's output, and thereby enhance the system's credibility and utility. A prototype system is constructed to be used as a decision support tool in a National Science Foundation research program. The researcher has spent the last year at the NSF collecting the knowledge implemented in the prototype system.

Le diagnostic du cancer du sein est une activité humaine qui dépend du contexte dans lequel il est réalisé. Ce contexte se traduit par l'existence de très nombreux éléments qui rend l'automatisation de cette activité impossible. Depuis quelques années, la numérisation des lames (support de raisonnement) a incité les pathologistes à passer à l'analyse d'image de lames à l'écran. Cette migration a offre la possibilité d'une procéduralisation au moins partielle de leurs méthodes d'analyse. Dans le cadre de cette thèse, nous nous sommes intéressés à l'activité d'analyse d'une image de lame par un pathologiste qui est modélisée dans le formalisme des graphes contextuels dans le but de proposer une solution permettant d'assister les pathologistes dans leurs diagnostics. Notre Consultant fait partie des Systèmes d'Assistance Intelligents basés sur le Contexte. L'outil principal du Consultant est basé sur la Simulation à partir de pratiques expertes décrites dans un graphe contextuel. En partant d'une image que le pathologiste doit analyser, le simulateur va développer une pratique qui est la plus adaptée au contexte de travail. Le résultat de la simulation va donc être la pratique résultante et toutes les informations sur la manière dont cette pratique a été obtenue. Le consultant propose alors à l'utilisateur une visualisation des résultats des simulations réalisées permettant de les analyser et de les comparer. / Breast cancer diagnosis is a human activity that is context-dependent. The context contains a large number of elements that limits strongly any possibility de complete automation. Recently, digitization of slides (reasoning support) prompted pathologists to migrate from slide analysis under microscope to slide image analysis on the screen. This migration offers a possibility of partial proceduralization of their analysis methods. In this thesis, we are interested on the activity of slide image analysis by a pathologist that is modeled in the Contextual-Graphs formalism with the goal to propose a solution to support pathologists in their diagnosis. Our Consultant belongs to the class of Context based Intelligent Assistant Systems. The main tool of the consultant is based on the simulation of expert practices described in a contextual graph. Starting from an image to analyze, the simulator will develop a practice that is the most adapted to the working context. The output of the simulation is the resulting practice and ll information about its development. The consultant proposes to the user a visualization of the different results for analysis and comparison.

Context-based Reasoning (CxBR) and Contextual Graphs (CxGs) involve the modeling of human behavior in autonomous and decision-support situations in which optimal human decision-making is of utmost importance. Both formalisms use the notion of contexts to allow the implementation of intelligent agents equipped with a context sensitive knowledge base. However, CxBR uses a set of discrete contexts, implying that models created using CxBR operate within one context at a given time interval. CxGs use a continuous context-based representation for a given problem-solving scenario for decision-support processes. Both formalisms use contexts dynamically by continuously changing between necessary contexts as needed in appropriate instances. This thesis identifies a synergy between these two formalisms by looking into their similarities and differences. It became clear during the research that each paradigm was designed with a very specific family of problems in mind. Thus, CXBR best implements models of autonomous agents in environment, while CxGs is best implemented in a decision support setting that requires the development of decision-making procedures. Cross applications were implemented on each and the results are discussed.